code-audit
Skill3 starsChanged 23 days agoMITView on GitHub
Full code review of a branch, diff or commit with open-code-review: OCR picks the files and rules, the agent reviews. Use for an audit or a complete review. Requires the `ocr` CLI.
- Installs packages
27 other projects use a version of this.
Adopted by
Most recently taken up by
- arcasilesgroup/ai-engineeringtheir own version, first seen Nov 8, 2026
- pietz/skillstheir own version, first seen Nov 8, 2026
- lza6/claw-code-tingfengtheir own version, first seen Nov 1, 2026
- VorElze/hermes-office-skillstheir own version, first seen Nov 1, 2026
- greglas75/zuvotheir own version, first seen Oct 16, 2026
- folkjrk/claude-skillstheir own version, first seen Oct 13, 2026
Used with
Projects with it also use database-security, malware-analysis and 6 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
JeremyMorganSkilldatabase-security
Examines all database interactions for injection, access control, encryption, and data-exposure risks. Use when auditing database and data-layer security.
Also in 3 projects that use this
tsaleSkillmalware-analysis
Professional malware analysis workflow for PE executables and suspicious files. Triggers on file uploads with requests like "analyze this malware", "analyze this sample", "what does this executable do", "check this file for malware", or any request to examine suspicious files. Performs static analysis, threat intelligence triage, behavioral inference, and produces analyst-grade reports with reasoned conclusions.
Also in 3 projects that use this
jefflesterSkillapi-security
API security best practices and common vulnerability prevention. Enforces security checks for authentication, input validation, SQL injection, XSS, and OWASP Top 10 vulnerabilities. Use when building or modifying APIs.
Also in 3 projects that use this
QiuChenlySkillreverse-engineering
专业二进制逆向工程分析技能。使用IDA Pro MCP工具分析二进制文件、反编译代码、识别漏洞、理解程序逻辑。当用户要求分析可执行文件、反汇编、逆向工程、漏洞挖掘、恶意软件分析时使用此技能。
Also in 3 projects that use this
SentrySkillui-design
Also in 3 projects that use this
GitHubSkillrefactor
Surgical code refactoring to improve maintainability without changing behavior. Covers extracting functions, renaming variables, breaking down god functions, improving type safety, eliminating code smells, and applying design patterns. Less drastic than repo-rebuilder; use for gradual improvements.
Also in 3 projects that use this
Other versions27 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 27
- zhaoxuya520/reverse-skill-private★ 40ksame name
- zhaoxuya520/reverse-skill★ 38ksame name
- epicenter-md/epicenter★ 4.8ksame name
- EpicenterHQ/epicenter★ 4.8ksame name
- pass-with-high-score/blockads-android★ 2.7ksame name
- 3stoneBrother/code-audit★ 893same name
- aspi6246/Claude-Code-Skills-for-Academics★ 153same name
- arcasilesgroup/ai-engineering★ 65same name
- hawkyre/hawk-skills★ 30same name
- greglas75/zuvo★ 7same name
17 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository51 other files it gives its agents.
- guidelines/CLAUDE.mdCLAUDE.md
- animate-expoSkill
- animateSkill
- animation-vocabularySkill
- apple-designSkill
- ask-sonnerSkill
- batch-grill-meSkill
- bi-dashboardsSkill
- bouw-loopSkill
- brandkitSkill
- commit-disciplineSkill
- councilSkill
- createlooppromptSkill
- data-visualizationSkill
- design-taste-frontendSkill
- diagram-designSkill
- dicht-loopSkill
- e2e-rulesSkill
- e2eSkill
- emil-design-engSkill
- find-animation-opportunitiesSkill
- find-bugsSkill
- fixing-accessibilitySkill
- fix-loopSkill
- frontend-gotchasSkill
- goalSkill
- improve-animationsSkill
- keten-loopSkill
- make-interfaces-feel-betterSkill
- mobile-nativeSkill
- office-docsSkill
- pick-ui-librarySkill
- polijst-loopSkill
- polpohire-designSkill
- pre-pr-gatesSkill
- projectstructuurSkill
- prototypeSkill
- readmeSkill
- reaSkill
- redesign-existing-projectsSkill
- render-proofSkill
- repo-hygieneSkill
- review-animationsSkill
- skill-finderSkill
- speur-loopSkill
- supergoalSkill
- systematic-debuggingSkill
- theme-selectorSkill
- transitions-devSkill
- ux-heuristicsSkill
- waak-loopSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 5 are distinctive, and 5 are very specific to this project.
0
Common
Most of the 17 edited versions we read keep these.
5
Distinctive
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 21
Start met /code-audit. Upstream: alibaba/open-code-review at 23992511c8876f51c1a31e52938fac02ac42f842, skills/open-code-review-delegate.
- Very specific: line 23
Use only ocr delegate with the active host session.
- Distinctive: line 26
Never publish findings, commit, merge or deploy without the user's authorization.
- Distinctive: line 66
Use git directly based on the mode/ref info from Step 1:
- Very specific: line 88
Create a checklist containing every reviewable_files entry.
- Very specific: line 90
Use (path, status) as the checklist identity.
- Very specific: line 114
Before reporting, verify that every previewed file is accounted for.
- Distinctive: line 126
If the user requested "review and fix":
- Distinctive: line 167
Do not silently truncate the source file.
- Distinctive: line 177
If a faithful summary is not possible, omit the OCR background entirely and read the original material directly during the review.
“Common” is measured: kept by at least 6 in 10 of the 17 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Open Code Review — Delegation Mode
Start met /code-audit. Upstream: alibaba/open-code-review at
23992511c8876f51c1a31e52938fac02ac42f842, skills/open-code-review-delegate.
Use only ocr delegate with the active host session. Do not configure an API
provider, switch models, or run ocr review/ocr scan as a fallback. Installation
is not review evidence. Keep source, secrets and personal data on your own Claude seat.
Never publish findings, commit, merge or deploy without the user's authorization.
Compare the preview with git diff --name-status and untracked files. Review
dependency manifests and tests even when OCR excludes them by default. Report
coverage against the Git inventory, not only OCR's filtered list. A partial
review never establishes that a release is safe to merge.
A skill for performing AI code review where OCR provides deterministic engineering (file filtering, rule resolution) and the host agent performs the actual review using its own intelligence and tools.
Workflow
Step 1: Preview — Determine What to Review
ocr delegate preview --format json [--from <ref> --to <ref>] [--commit <hash>] [--exclude <patterns>]This outputs:
- mode (workspace / range / commit)
- from / to / commit / merge_base — ref metadata for constructing git commands
- Reviewable file list — paths, status, insertions/deletions
- Excluded files — with exclusion reason
Common invocations:
| Scenario | Command |
| Workspace changes | ocr delegate preview |
| Branch comparison | ocr delegate preview --from main --to feature |
| Single commit | ocr delegate preview -c abc123 |
Step 2: Get Rules for Files
ocr delegate rule --format json <path1> <path2> ...Pass the reviewable file paths from Step 1. Output is grouped by rule content — files sharing the same rule appear under one group, avoiding repetition.
Step 3: Get Diffs
Use git directly based on the mode/ref info from Step 1:
Range mode (merge_base provided in preview output):
git diff <merge_base>..<to> -- <path>Commit mode:
git show <commit> -- <path>Workspace mode:
# Tracked files
git diff HEAD -- <path>
# New untracked files — read directly (entire file is new code)
cat <path>Step 4: Review Each File
Create a checklist containing every reviewable_files entry. For each reviewable file:
Use (path, status) as the checklist identity. Workspace mode can report the same path twice when a staged deletion is followed by an untracked recreation.
- Get its diff (Step 3)
- Consult its Rule Group (from Step 2) for the review checklist
- Conduct a thorough review, using appropriate context tools as needed
- Mark the file
reviewed, orskippedwith a concrete reason
For large changes, review in bounded batches grouped by shared rules and diff size. Do not stop after finding the first high-severity issue.
Step 5: Format Output
Each comment must follow this structure:
| Field | Type | Required | Description |
| path | string | yes | Relative file path |
| content | string | yes | Review comment describing the issue |
| start_line | integer | no | Start line in the new file |
| end_line | integer | no | End line in the new file |
| category | enum | no | bug, security, performance, maintainability, test, style, documentation, other |
| severity | enum | no | critical, high, medium, low |
Step 6: Classify and Report
Before reporting, verify that every previewed file is accounted for. Include total_files, reviewed_files, skipped_files, and coverage_rate in the summary. A skipped file must include its reason.
Group findings by severity:
- Critical/High: Bugs, security issues, data loss risks — always report
- Medium: Performance concerns, error handling gaps, maintainability issues — report with context
- Low: Style nits, minor suggestions — report only if clearly valuable
Discard likely false positives silently.
Step 7: Fix (Optional)
If the user requested "review and fix":
- Apply High/Critical fixes directly
- Describe Medium fixes that require manual intervention
- Skip Low-priority items unless trivial
Sub-commands Reference
| Command | Purpose |
ocr delegate preview | Which files to review + mode/ref metadata |
ocr delegate rule <path...> | Review rules grouped by content |
Shared Flags
| Flag | Description |
--from <ref> | Source ref for range mode |
--to <ref> | Target ref for range mode |
-c, --commit <hash> | Single commit mode |
--repo <path> | Repository root (default: cwd) |
--rule <path> | Custom rule.json path |
--exclude <patterns> | Comma-separated exclude patterns |
-b, --background <text> | Business context |
-B, --background-file <path> | Business context from Markdown file (takes precedence over -b) |
-f, --format <text|json> | Output format; use json for agent integrations |
Gotchas
- No LLM needed on OCR side — delegation mode never calls an LLM. All intelligence comes from the host agent.
- Rules are grouped — Files sharing the same rule are grouped together in the output. You can pass any number of paths per call; for large changes, fetch rules per-batch as you review.
- Working directory matters —
ocr delegateoperates on the Git repo at the current directory. Use--repo /pathto override. - Untracked files in workspace mode —
previewincludes untracked files. For these, read the file directly instead of usinggit diff. - Background context — pass
--backgroundtopreviewwhen you have requirement context; it appears in the output for your reference during review. - Coverage is mandatory — every
reviewable_filesentry must end as reviewed or explicitly skipped; do not silently omit files.
Recovering Oversized Background Context
--background-file has two independent limits. The raw file must not exceed
1 MiB, and the sanitized content must not exceed 8000 characters. Either
condition aborts the command. When the command reports either limit:
- Do not silently truncate the source file.
- Summarize the original material while preserving its requirements, constraints, acceptance criteria, and other review-critical details.
- Retry the affected command by passing the summary as one shell-safe
argument (for example, use a quoted/escaped argument produced by the host
shell, or write it to a new size-bounded file and pass that file). Do not
place untrusted summary text directly in a double-quoted shell template;
$(), backticks, quotes, and variable references can still be evaluated. Omit the original--background-fileso the CLI does not reload the same oversized file and fail again. - If a faithful summary is not possible, omit the OCR background entirely and read the original material directly during the review.
Troubleshooting CLI Version Compatibility
The --format flag is available in ocr v1.9.0 and later. The Skill and the
installed CLI can be updated independently. If a requested preview or rule
command with --format json fails specifically with unknown flag: --format,
rerun it without the flag and use text output for the rest of the delegation
run. Preserve the explicit mode, ref, file, and rule information from that
output; do not parse text output as JSON or invent missing schema fields. Do
not retry without the flag for any other error; report it and stop the affected
workflow.
The host-agent Skill may consume the equivalent text output to complete its
review checklist. Programmatic integrations that require schema_version or
other JSON fields must require a JSON-capable CLI instead: verify with
ocr --version and upgrade when necessary:
npm install -g @alibaba-group/open-code-reviewDoes it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

